Outer Step 1. Inner Step 334. Batch Size 276

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5146199,
-    5146203,
-    5146207,
-    5146211,
-    5146216,
-    5146220,
-    5146224,
-    5146228,
-    5146232,
-    5146236
+    5146270,
+    5146274,
+    5146278,
+    5146282,
+    5146286,
+    5146290,
+    5146294,
+    5146298,
+    5146302,
+    5146306
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 324,
+  "inner_step": 334,
   "inner_steps": 0,
   "last_allreduce_block": 5143202,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542d9afd25b24ade1d3e0e6367e2aba3832e034d22a8ef0896ec4412099cd37e
+oid sha256:0e85f01141ba6e0fb4d7fb7956b79477cbf44874ef9054c9f8d05cf2c93dd3da
 size 8081781770

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de58a71f3b06c4a6feb0285e47e47b086e89b56bf496c0885efb75e7b46901dd
+oid sha256:b24b969c2506396918e7ffc6b32673bba0c13f0af9089ef99d125fefa5aca691
 size 4040701744